Related papers: High-Entropy Tokens as Multimodal Failure Points i…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a central approach for improving the reasoning ability of large language models. Recent work studies RLVR through token entropy, arguing that high-entropy tokens drive…

The rise of generative neural networks has triggered an increased demand for intellectual property (IP) protection in generated content. Deep watermarking techniques, recognized for their flexibility in IP protection, have garnered…

Selective prediction systems can mitigate harms resulting from language model hallucinations by abstaining from answering in high-risk cases. Uncertainty quantification techniques are often employed to identify such cases, but are rarely…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks. However, the increasing demand for high-resolution image and long-video understanding results in substantial token counts,…

Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. Traditional approaches often depend on meticulously designed prompts, high-quality examples, or additional reward models for…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated tokens depend on visual modalities remains poorly understood,…

Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications. However, as they are becoming increasingly prevalent, ensuring their robustness against adversarial attacks is paramount. This work…

Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations, enabling attackers to optimize on surrogate models and manipulate black-box VLM outputs. Prior targeted transfer attacks often overfit…

Large Language Models (LLMs) have achieved remarkable success across domains such as healthcare, education, and cybersecurity. However, this openness also introduces significant security risks, particularly through embedding space…

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle…

Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propose a fundamentally different paradigm: entropic\-time…

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries.…

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…

RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. However, entropy only measures diversity within the same input,…

Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime…